Groundtruth – Stop hook that blocks Claude Code from saying done
Stop hook enforcement beats trusting agents to self-verify their work.

Adapts accessibility-agents hook architecture to enforce voice instead of WCAG compliance.
Teams using Claude Code for content and copywriting
accessibility-agents
Stop hook enforcement beats trusting agents to self-verify their work.
Clever WIP visibility for Claude, but mostly a bash script solving a Claude-specific friction point.
Claude Code safety gate that blocks breaking changes; solves real foot-gun but limited to one AI tool.
Blocks gh run watch rate-limit burns and pkill -f disasters before they happen.
Independent critic agent with no access to builder's reasoning catches blind spots.
Six shell hooks hard-block RCE and exfiltration before Claude Code executes anything.